© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85193
    Prev
    Next
    INDEX
    Explanations

    specific surnames

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on occurrences of the surname “Baldwin.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -2.56
    诣
    -2.41
     finnas
    -2.39
     cemented
    -2.38
     principally
    -2.34
    autres
    -2.31
    of
    -2.28
    滂
    -2.27
    してい
    -2.23
    R
    -2.22
    POSITIVE LOGITS
    ’
    3.44
    </i>
    3.34
    鵟
    2.45
    </td>
    2.44
      
    2.42
     $
    2.34
    1
    2.28
    "));
    2.22
     “
    2.19
     két
    2.19
    Activations Density 0.011%

    No Known Activations